Skip to content

stevesolun/ctx / .agents/skills/teach

Teach a skill or concept at the user's current level, optionally preserving a lightweight multi-session learning record.

FileKindSize
GLOSSARY-FORMAT.mdmarkdown2.1 KB
LEARNING-RECORD-FORMAT.mdmarkdown2.7 KB
MISSION-FORMAT.mdmarkdown1.5 KB
RESOURCES-FORMAT.mdmarkdown1.9 KB
SKILL.mdskill md1.2 KB
agents/openai.yamlconfig139 B
references/teaching-principles.mdmarkdown1.2 KB

references/teaching-principles.md

View on GitHub
# Teaching principles

## Ground the work

- Tie lessons to a practical mission rather than an abstract content list.
- Estimate the learner's current understanding from conversation and prior
  work; revise that estimate as evidence arrives.
- Keep each lesson within a productive challenge range: achievable with effort,
  but not automatic.

## Build durable understanding

- Distinguish immediate fluency from long-term retention.
- Use retrieval practice, spacing, interleaving, examples, and feedback when
  they fit the material and learner.
- Teach knowledge in service of a skill or decision instead of maximizing
  coverage.
- Encourage real-world practice when it adds evidence that exercises cannot.

## Preserve state selectively

For continuing work, choose only useful artifacts:

- `MISSION.md` for the learner's purpose.
- `RESOURCES.md` for vetted sources.
- `learning-records/` for durable insights and changes in understanding.
- `reference/` for reusable summaries.
- `lessons/` for lesson artifacts when a file is better than conversation.

Avoid creating empty scaffolding. Existing format files in the skill directory
are optional templates, not mandatory outputs.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall